Throughput Scaling Research Articles

Throughput analysis of one-dimensional vehicular ad hoc networks

We consider content distribution in a one-dimensional vehicular ad hoc network. We assume that a file is encoded using fountain code, and the encoded message is cached at infostations. Vehicles are allowed to download data packets from infostations, which are placed along a highway. In addition, two vehicles can exchange packets with each other when they are in proximity. As long as a vehicle has received enough packets from infostations or from other vehicles, the original file can be recovered. In this work, we derive closed-form expressions for the average per-node throughput, under both discrete and continuous velocity distributions for the vehicles. Our result shows that the average per-node throughput can be expressed as a linear function of the densities of different classes of nodes in the highway. This result implies that the average per-node throughput scales linearly with vehicle arrival rate, and the average system throughput scales quadratically with vehicle arrival rate. Besides, system throughput reduces when overall mobility increases.

Большие данные: современные подходы к хранению и обработке

Big data challenged traditional storage and analysis systems in several new ways. In this paper we try to figure out how to overcome this challenges, why it's not possible to make it efficiently and describe three modern approaches to big data handling: NoSQL, MapReduce and real-time stream processing. The first section of the paper is the introduction. The second section discuss main issues of Big Data: volume, diversity, velocity, and value. The third section describes different approaches to solving the problem of Big Data. Traditionally one might use a relational DBMS. The paper propose some steps that allow to continue RDBMS using when it’s capacity becomes not enough. Another way is to use a NoSQL approach. The basic ideas of the NoSQL approach are: simplification, high throughput, and unlimited scaling out. Different kinds of NoSQL stores allow to use such systems in different applications of Big Data. MapReduce and it’s free implementation Hadoop may be used to provide scaling out Big Data analytics. Finally, several data management products support real time stream processing under Big Data. The paper briefly overviews these products. The final section of the paper is the conclusion.

Facile fabrication of nanofluidic diode membranes using anodic aluminium oxide

Active control of ion transport plays important roles in chemical and biological analytical processes. Nanofluidic systems hold the promise for such control through electrostatic interaction between ions and channel surfaces. Most existing experiments rely on planar geometry where the nanochannels are generally very long and shallow with large aspect ratios. Based on this configuration the concepts of nanofluidic gating and rectification have been successfully demonstrated. However, device minimization and throughput scaling remain significant challenges. We report here an innovative and facile realization of hetero-structured Al(2)O(3)/SiO(2) (Si) nanopore array membranes by using pattern transfer of self-organized nanopore structures of anodic aluminum oxide (AAO). Thanks to the opposite surface charge states of Al(2)O(3) (positive) and SiO(2) (negative), the membrane exhibits clear rectification of ion current in electrolyte solutions with very low aspect ratios compared to previous approaches. Our hetero-structured nanopore arrays provide a valuable platform for high throughput applications such as molecular separation, chemical processors and energy conversion.

Throughput Scaling Laws for Vehicular Ad Hoc Networks

This paper investigates throughput scaling laws for Vehicular Ad Hoc Networks (VANETs). We show that the road geometry greatly affects the throughput of a VANET. To this end we introduce the notion of sparseness to capture the geometrical properties of roads. We then start by addressing scaling laws for single roads. We shall see that even a single road can have very different scaling behaviors based on its path trajectory. Scaling laws for more complex systems such as downtown grids and general road systems are studied next. Here, the concept of road-connectivity plays a major role in determining the scaling behavior. In our analysis we account for a spectrum of node distributions that represent different vehicular traffic conditions. We also introduce the distance-limited throughput, a notion of throughput especially introduced for VANET-specific applications, and see how it scales in a single road system and in the presence of infrastructure. Our results are obtained by combining geometrical analysis, network flow arguments, and the probabilistic study of VANETs.

Spectrum Sharing SDMA with Limited Feedback: Throughput Analysis

In the context of effective usage of a scarce spectrum resource, emerging wireless communication standards will demand spectrum sharing with existing systems as well as multiple access with higher spectral efficiency. We mathematically analyze the sum throughput of a spectrum sharing space-division multiple access (SDMA) system, which forms a transmit null in the direction of other coexisting systems while satisfying orthogonal beamforming constraints. For a large number of users N, the SDMA throughput scales as logN at high signal-to-noise ratio (SNR) ((J-1)loglogN at normal SNR), where J is the number of transmit antennas. This indicates that multiplexing gain of the spectrum sharing SDMA is times less than that of the non-spectrum sharing SDMA only using orthogonal beamforming, whereas no loss in multiuser diversity gain. Although the spectrum sharing SDMA always has lower throughput compared to the non-spectrum sharing SDMA in the non-coexistence scenario, it offers an intriguing opportunity to reuse spectrum already allocated to other coexisting systems.

Rate-Constrained Wireless Networks With Fading Channels: Interference-Limited and Noise-Limited Regimes

A network of n wireless communication links is considered in a Rayleigh fading environment. It is assumed that each link can be active and transmit with a constant power <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</i> or remain silent. The objective is to maximize the number of active links such that each active link can transmit with a constant rate λ. In a Rayleigh fading environment, an upper bound is derived that shows the number of active links scales at most like 1/λ log n. To obtain a lower bound, a decentralized link activation strategy is described and analyzed. It is shown that for small values of λ, the number of supported links by this strategy meets the upper bound; however, as λ grows, this number becomes far below the upper bound. To shrink the gap between the upper bound and the achievability result, a modified link activation strategy is proposed and analyzed based on some results from random graph theory. It is shown that this modified strategy performs very close to the optimum. Specifically, this strategy is asymptotically almost surely optimum when λ approaches ∞ or 0. It turns out that the optimality results are obtained in an interference-limited regime. It is demonstrated that, by proper selection of the algorithm parameters, the proposed scheme also allows the network to operate in a noise-limited regime in which the transmission rates can be adjusted by the transmission powers. The price for this flexibility is a decrease in the throughput scaling law by a multiplicative factor of loglog <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> . Finally, both decentralized and centralized schemes are evaluated in a distance-dependent fading environment with a path loss exponent of m and are shown to achieve throughput that scale like Θ( n <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(m</sup> / <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m+2)</sup> log n ) and Θ(n <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[(m(2)+2m)/( m(2)+2m+4)]</sup> ), respectively.

One-Hop Throughput of Wireless Networks with Random Connections

We consider one-hop communication in wireless networks with random connections. In the random connection model, the channel powers between different nodes are drawn from a common distribution in an i.i.d. manner. In a wireless network with n nodes, a simple one-hop scheme achieving the throughput scaling of order n <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1/3-δ</sup> , for any arbitrarily small δ>;0, is proposed. This scheme is based on maximizing the number of successful concurrent transmissions. Such achievable throughput, along with the order n <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1/3</sup> upper bound derived by Cui et al., characterizes the throughput of one-hop schemes for the class of connection models with distribution having finite mean and variance.

Throughput and delay scaling laws for mobile overlaid wireless networks

In this paper, we study the throughput and delay scaling laws over two coexisting mobile networks. The primary network consists of n randomly distributed primary nodes which can operate as if the secondary network is absent. However, the secondary network with a higher density m=nβ, β>1 is required to adjust its protocol. By considering that both the primary and the secondary networks move according to random walk mobility model, we propose a multi-hop transmission scheme, and show that the secondary network can achieve the same throughput and delay tradeoff scaling law as in stand-alone network Ds(m)=Θ(mλs(m)). Furthermore, for primary network, it is shown that the tradeoff scaling law is given by Dp(n)=Θ(nlognλp(n)), when the primary node is chosen as relay node. If the relay node is a secondary node, the scaling law is Dp(n)=Θ(nβlognλp(n)). The novelties of this paper lie in: (i) detailed study of the delay scaling law for the primary network in the complex scenario where both the primary and the secondary networks are mobile; (ii) the impact of buffer delay on the two networks due to the presence of preservation region. We explicitly analyze the buffer delay and obtain an expression as DSRII(m)=Θ(1/nβ−1as(m)).

Experiences in building and scaling an enterprise application on multicore systems

SUMMARYEven though Java is the de facto programming language for enterprise applications, there exist only a limited number of Java‐based benchmarks to understand the performance on emerging multicore systems. To bridge this gap, this paper presents a report generation benchmark that is developed on top of Open Source Apache Geronimo's DayTrader benchmark. Report generation and rendering is at the heart of many enterprise business analytics and business intelligence software products, and it is used by many enterprise applications. We evaluate the performance scalability of this benchmark on a state‐of‐the‐art Power7 multicore system with 8 Power7 cores and 32 hardware threads. The benchmark throughput scales linearly up to eight hardware threads, but beyond that point, the throughput falls sharply. Significant locking in the Java class libraries for non‐shared objects results in this performance drop. Splitting the locks on these shared classes results in near linear scaling from eight to 32 threads and improved the throughput by 80%. We also show that the Linux operating system load balancing could result in a degraded application performance in hardware multithreaded systems and simultaneous‐multithreads‐aware task scheduling results in uniform core‐resource utilization as well as improved application performance. Copyright © 2011 John Wiley &amp; Sons, Ltd.

Green Wave Sleep Scheduling: Optimizing Latency and Throughput in Duty Cycling Wireless Networks

Duty cycling or periodic sleep scheduling of RF transceivers of nodes in a wireless ad hoc or sensor network can significantly reduce energy consumption. This paper sheds light on the fundamental limits of the end-to-end data delivery latency and the per-flow throughput in a wireless network with multiple interfering flows, in the presence of "coordinated" duty cycling. We propose green wave sleep scheduling (GWSS) - inspired by synchronized traffic lights - for scheduling sleep-wake slots and routing data in a duty cycling wireless network, whose performance can approach the aforementioned limits. Particularly, we derive a general latency lower bound and show that GWSS is latency optimal on various structured topologies, such as the line, grid and the tree, at low traffic load. For an arbitrary network, finding a solution to the delay-efficient sleep scheduling problem is NP-hard. But for the 2D grid topology, we show that a non-interfering construction of GWSS is optimal in the sense of scaling laws of latency and capacity. Finally, using results from percolation theory, we extend GWSS to random wireless networks, where nodes are placed in a square area according to the Poisson point process. Aided by strong numerical evidence for a new conjecture on percolation on a semi-directed lattice that we propose, we demonstrate the latency optimality of GWSS on a random extended network, i.e., for an area-n random network with unit-density-Poisson distributed nodes, and a node-active (duty-cycling) rate p, GWSS can achieve a per-flow throughput scaling of T(n, p) = Ω(p/√n) bits/sec and latency D(n, p) scaling of O(√n) + O(1/p) hops/packet/flow.

Optimized cluster-based filtering algorithm for graph metadata

With the increasing amount of information on the Web and the proliferation of RSS offerings, efficient graph-based metadata filtering algorithm for large scale information dissemination is very important today. Matching graph-based documents is expensive due to the expressiveness of the language. The centralized architecture does not work well for the large scale information dissemination service. To address these problems, in this paper we develop a cluster-based publish/subscribe system for filtering graph-based RSS documents. Essentially, we develop two indexing algorithms to enable workload distribution and cluster-based filtering. Furthermore, we proposed an optimized graph matching algorithm which speeds up the constraint evaluation for subscriptions. The experimental results show that we can support one million subscriptions on a compute cluster with 5–20 nodes and the throughput scales linearly with the number of cluster nodes.

On multicast throughput scaling of hybrid wireless networks with general node density

In this paper, we consider hybrid wireless networks with a general node density λ ∈ [1, n], where n ad hoc nodes are uniformly distributed and m base stations (BSs) are regularly placed in a square region A ( n , A ) = 1 , A × 1 , A with A ∈ [1, n]. We focus on multicast sessions in which each ad hoc node as a user chooses randomly d ad hoc nodes as its destinations. Specifically, when d = 1 (or d = n − 1), a multicast session is essentially a unicast (or broadcast) session. We study the asymptotic multicast throughput for such a hybrid wireless network according to different cases in terms of m ∈ [1, n] and d ∈ [1, n], as n → ∞. To be specific, we design two types of multicast schemes, called hybrid scheme and BS- based scheme, respectively. For the hybrid scheme, there are two alternative routing backbones: sparse backbones and dense backbones. Particularly, according to different regimes of the node density λ = n A , we derive the thresholds in terms of m and d. Depending on these thresholds, we determine which scheme is preferred for the better performance of network throughput.

Refined Routing Algorithm in Hybrid Networks with Different Transmission Rates

In this paper, a low-complexity routing strategy is introduced for a hybrid network in which n wireless nodes are randomly located and multiple base stations (BSs) are used. We allow different transmission rates according to the geographic location of each source in the network. Our achievable scheme consists of the following two routing schemes: a BS-based single-hop (SH) routing in the up/downlink and conventional multi-hop transmission. Specifically, in the proposed BS-based scheme, when a source-destination (S-D) pair is inside the center region with respect to its BS, the source is allowed to transmit data to its closest BS via SH. Our results indicate that a logarithmic boost (i.e., power gain) is provided in the throughput scaling law, compared to the conventional schemes, as the number of BSs is greater than a certain threshold. The gain comes from the fact that S-D pairs in their center regions can exploit per-node transmission rates log n due to the increased received signal power from/to their closest BS.

수중 애드 혹 네트워크에서의 시스템 모델링 및 용량 스케일링 법칙에 대하여

In this paper, we introduce system and channel modeling for an underwater ad hoc acoustic network with n regularly located nodes， and then analyze capacity scaling laws based on the model. A narrow-band model is assumed where the carrier frequency is allowed to scale as a function of n. In the network, we characterize in attenuation parameter that depends on the frequency scaling as well as the transmission distance. A cut-set upper bound on the throughput scaling is then derived in extended networks having unit node density. Our result indicates that the upper bound is inversely proportional to the attenuation parameter, thus resulting in a power-limited network. Furthermore, we describe an achievable scheme based on the simple nearest-neighbor multi-hop (MH) transmission. It is shown under extended networks that the MH scheme is order-optimal for all the operating regimes expressed as functions of the attenuation parameter.

Throughput and delay analysis for hybrid radio-frequency and free-space-optical (RF/FSO) networks

In this paper the per-node throughput and end-to-end delay of randomly deployed (i.e. ad-hoc) hybrid radio frequency - free space optics (RF/FSO) networks are studied. The hybrid RF/FSO network consists of an RF ad hoc network of n nodes, f(n) of them, termed `super nodes', are equipped with an additional FSO transceiver with transmission range s(n). Every RF and FSO transceiver is able to transmit at a maximum data rate of W 1 and W 2 bits/sec, respectively. An upper bound on the per node throughput capacity is derived. In order to prove that this upper bound is achievable, a hybrid routing scheme is designed whereby the data traffic is divided into two classes and assigned different forwarding strategies. The capacity improvement with the support of FSO nodes is evaluated and compared against the corresponding results for pure RF wireless networks. Under optimal throughput scaling, the scaling of average end-to-end delay is derived. A significant gain in throughput capacity and a notable reduction in delay will be achieved if $$f(n) = \Upomega\left(\frac{1}{s(n)}\sqrt{\frac{n}{\log n}}\cdot \frac{W_1}{W_2} \right)$$ . Furthermore, it is found that for fixed W 1, f(n) and n where f(n) < n, there is no capacity incentive to increase the FSO data rate beyond a critical value. In addition, both throughput and delay can achieve linear scaling by properly adjusting the FSO transmission range and the number of FSO nodes.

Multiuser Diversity Gain in Cognitive Networks

Dynamic allocation of resources to the best link in large multiuser networks offers considerable improvement in spectral efficiency. This gain, often referred to as multiuser diversity gain, can be cast as double-logarithmic growth of the network throughput with the number of users. In this paper, we consider large cognitive networks granted concurrent spectrum access with license-holding users. The primary network affords to share its underutilized spectrum bands with the secondary users. We assess the optimal multiuser diversity gain in the cognitive networks by quantifying how the sum-rate throughput of the network scales with the number of secondary users. For this purpose, we look at the optimal pairing of spectrum bands and secondary users, which is supervised by a central entity fully aware of the instantaneous channel conditions, and show that the throughput of the cognitive network scales double-logarithmically with the number of secondary users (N) and linearly with the number of available spectrum bands (M), i.e., M log log N. We then propose a distributed spectrum allocation scheme, which does not necessitate a central controller or any information exchange among different secondary users and still obeys the optimal throughput scaling law. This scheme requires that some secondary transmitter-receiver pairs exchange log M information bits among themselves. We also show that the aggregate amount of information exchange between secondary transmitter-receiver pairs is asymptotically equal to M log M. Finally, we show that our distributed scheme guarantees fairness among the secondary users, meaning that they are equally likely to get access to an available spectrum band.

Throughput Scaling of Wireless Ad Hoc Networks With No Side Information

This letter studies the throughput of wireless ad hoc networks in which neither the source nodes nor the destination nodes have channel state information. Work reported in has shown that in the regime of a large network with a total number of nodes n → ∞, the throughput scales at most as log log n. We present a scheme that achieves a throughput scaling of Θ(log n) for the Gauss-Markov fading process and for network sizes of practical interest.

Sustainable Throughput of Wireless LANs with Multipacket Reception Capability under Bounded Delay-Moment Requirements

With the rapid proliferation of broadband wireless services, it is of paramount importance to understand how fast data can be sent through a wireless local area network (WLAN). Thanks to a large body of research following the seminal work of Bianchi, WLAN throughput under saturated traffic condition has been well understood. By contrast, prior investigations on throughput performance under unsaturated traffic condition was largely based on phenomenological observations, which lead to a common misconception that WLAN can support a traffic load as high as saturation throughput, if not higher, under nonsaturation condition. In this paper, we show through rigorous analysis that this misconception may result in unacceptable quality of service: mean packet delay and delay jitter may approach infinity even when the traffic load is far below the saturation throughput. Hence, saturation throughput is not a sound measure of WLAN capacity under nonsaturation condition. To bridge the gap, we define safe-bounded-mean-delay (SBMD) throughput and safe-bounded-delay-jitter (SBDJ) throughput that reflect the actual network capacity users can enjoy when they require finite mean delay and delay jitter, respectively. Our earlier work proved that in a WLAN with multi-packet reception (MPR) capability, saturation throughput scales superlinearly with the MPR capability of the network. This paper extends the investigation to the nonsaturation case and shows that superlinear scaling also holds for SBMD and SBDJ throughputs. Our results here complete the demonstration of MPR as a powerful capacity-enhancement technique for WLAN under both saturation and nonsaturation conditions.

Throughput Scaling of Wireless Networks With Random Connections

This work studies the throughput scaling laws of ad hoc wireless networks in the limit of a large number of nodes. A random connections model is assumed in which the channel connections between the nodes are drawn independently from a common distribution. Transmitting nodes are subject to an on-off strategy, and receiving nodes employ conventional single-user decoding. The following results are proven: 1) for a class of connection models with finite mean and variance, the throughput scaling is upper-bounded by O(n1/3) for single-hop schemes, and O(n1/2) for two-hop (and multihop) schemes; 2) the Θ(n1/2) throughput scaling is achievable for a specific connection model by a two-hop opportunistic relaying scheme, which employs full, but only local channel state information (CSI) at the receivers, and partial CSI at the transmitters; 3) by relaxing the constraints of finite mean and variance of the connection model, linear throughput scaling Θ(n) is achievable with Pareto-type fading models.

Scaling Laws for Overlaid Wireless Networks: A Cognitive Radio Network versus a Primary Network

We study the scaling laws for the throughputs and delays of two coexisting wireless networks that operate in the same geographic region. The primary network consists of Poisson distributed legacy users of density <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> , and the secondary network consists of Poisson distributed cognitive users of density <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> , with <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">m</i> > <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> . The primary users have a higher priority to access the spectrum without particular considerations for the secondary users, while the secondary users have to act conservatively in order to limit the interference to the primary users. With a practical assumption that the secondary users only know the locations of the primary transmitters (not the primary receivers), we first show that both networks can achieve the same throughput scaling law as what Gupta and Kumar ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Trans. Inf. Theory,</i> vol. 46, no. 2, pp. 388-404, Mar. 2000) established for a standalone wireless network if proper transmission schemes are deployed, where a certain throughput is achievable for each individual secondary user (i.e., zero outage) with high probability. By using a fluid model, we also show that both networks can achieve the same delay-throughput tradeoff as the optimal one established by El Gamal ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Trans. Inf. Theory</i> , vol. 52, no. 6, pp. 2568-2592, Jun. 2006) for a standalone wireless network.